{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T06:01:35Z","timestamp":1772172095497,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1005727","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2017,9,15]],"date-time":"2017-09-15T00:00:00Z","timestamp":1505433600000}}],"reference-count":60,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2017,9,5]],"date-time":"2017-09-05T00:00:00Z","timestamp":1504569600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Centre of Excellence in Plant Energy Biology, Australian Research Council (AU)","award":["CE140100008"],"award-info":[{"award-number":["CE140100008"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"DOI":"10.1371\/journal.pcbi.1005727","type":"journal-article","created":{"date-parts":[[2017,9,5]],"date-time":"2017-09-05T13:47:13Z","timestamp":1504619233000},"page":"e1005727","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":45,"title":["kWIP: The k-mer weighted inner product, a de novo estimator of genetic similarity"],"prefix":"10.1371","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2466-1917","authenticated-orcid":true,"given":"Kevin D.","family":"Murray","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christfried","family":"Webers","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2302-9733","authenticated-orcid":true,"given":"Cheng Soon","family":"Ong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Justin","family":"Borevitz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norman","family":"Warthmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2017,9,5]]},"reference":[{"issue":"1","key":"ref1","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1038\/nrg2626","article-title":"Sequencing Technologies\u2014the next Generation","volume":"11","author":"ML Metzker","year":"2010","journal-title":"Nature Reviews Genetics"},{"issue":"6814","key":"ref2","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1038\/35048692","article-title":"Analysis of the Genome Sequence of the Flowering Plant Arabidopsis Thaliana","volume":"408","year":"2000","journal-title":"Nature"},{"issue":"7451","key":"ref3","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1038\/nature12211","article-title":"The Norway Spruce Genome Sequence and Conifer Genome Evolution","volume":"497","author":"B Nystedt","year":"2013","journal-title":"Nature"},{"issue":"5","key":"ref4","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1534\/g3.114.015784","article-title":"Mapping Bias Overestimates Reference Allele Frequencies at the HLA Genes in the 1000 Project Phase I Data","volume":"5","author":"DYC Brandt","year":"2015","journal-title":"G3: Genes|Genomes|Genetics"},{"issue":"2","key":"ref5","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1038\/ng.1028","article-title":"De Novo Assembly and Genotyping of Variants Using Colored de Bruijn Graphs","volume":"44","author":"Z Iqbal","year":"2012","journal-title":"Nature Genetics"},{"issue":"3","key":"ref6","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1105\/tpc.15.00502","article-title":"A Proposal Regarding Best Practices for Validating the Identity of Genetic Stocks and the Effects of Genetic Variants","volume":"28","author":"J Bergelson","year":"2016","journal-title":"The Plant Cell"},{"issue":"4","key":"ref7","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1111\/j.1558-5646.1963.tb03307.x","article-title":"The Compilospecies Concept","volume":"17","author":"JR Harlan","year":"1963","journal-title":"Evolution"},{"issue":"3","key":"ref8","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1093\/bib\/bbt067","article-title":"New Developments of Alignment-Free Sequence Comparison: Measures, Statistics and next-Generation Sequencing","volume":"15","author":"K Song","year":"2014","journal-title":"Briefings in Bioinformatics"},{"issue":"Part B","key":"ref9","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/j.compbiolchem.2014.10.007","article-title":"A Novel k-Word Relative Measure for Sequence Comparison","volume":"53","author":"J Tang","year":"2014","journal-title":"Computational Biology and Chemistry"},{"issue":"1","key":"ref10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2202\/1544-6115.1447","article-title":"Characterizing the D2 Statistic: Word Matches in Biological Sequences","volume":"8","author":"S For\u00eat","year":"2009","journal-title":"Statistical Applications in Genetics and Molecular Biology"},{"issue":"8","key":"ref11","doi-asserted-by":"crossref","first-page":"2677","DOI":"10.1073\/pnas.0813249106","article-title":"Alignment-Free Genome Comparison with Feature Frequency Profiles (FFP) and Optimal Resolutions","volume":"106","author":"GE Sims","year":"2009","journal-title":"Proceedings of the National Academy of Sciences of the United States of America"},{"key":"ref12","article-title":"Kmacs: The k-Mismatch Average Common Substring Approach to Alignment-Free Sequence Comparison","author":"CA Leimeister","year":"2014","journal-title":"Bioinformatics"},{"key":"ref13","article-title":"Fast Alignment-Free Sequence Comparison Using Spaced-Word Frequencies","author":"CA Leimeister","year":"2014","journal-title":"Bioinformatics"},{"issue":"7","key":"ref14","doi-asserted-by":"crossref","first-page":"e75","DOI":"10.1093\/nar\/gkt003","article-title":"Co-phylog: an assembly-free phylogenomic approach for closely related organisms","volume":"41","author":"H Yi","year":"2013","journal-title":"Nucleic acids research"},{"issue":"3","key":"ref15","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1093\/bib\/bbt068","article-title":"Information Theory Applications for Biological Sequence Analysis","volume":"15","author":"S Vinga","year":"2014","journal-title":"Briefings in Bioinformatics"},{"issue":"1","key":"ref16","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1186\/s13015-015-0032-x","article-title":"Estimating Evolutionary Distances between Genomic Sequences from Spaced-Word Matches","volume":"10","author":"B Morgenstern","year":"2015","journal-title":"Algorithms for Molecular Biology"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1186\/s12859-015-0806-7","article-title":"Cnidaria: Fast, Reference-Free Clustering of Raw and Assembled Genome and Transcriptome NGS Data","volume":"16","author":"SA Aflitos","year":"2015","journal-title":"BMC Bioinformatics"},{"issue":"1","key":"ref18","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1186\/s12864-015-1647-5","article-title":"An Assembly and Alignment-Free Method of Phylogeny Reconstruction from next-Generation Sequencing Data","volume":"16","author":"H Fan","year":"2015","journal-title":"BMC Genomics"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1186\/s13059-016-0997-x","article-title":"Mash: Fast Genome and Metagenome Distance Estimation Using MinHash","volume":"17","author":"BD Ondov","year":"2016","journal-title":"Genome Biology"},{"issue":"12","key":"ref20","doi-asserted-by":"crossref","first-page":"1615","DOI":"10.1089\/cmb.2009.0198","article-title":"Alignment-Free Sequence Comparison (I): Statistics and Power","volume":"16","author":"G Reinert","year":"2009","journal-title":"Journal of Computational Biology: A Journal of Computational Molecular Cell Biology"},{"issue":"11","key":"ref21","doi-asserted-by":"crossref","first-page":"1467","DOI":"10.1089\/cmb.2010.0056","article-title":"Alignment-Free Sequence Comparison (II): Theoretical Power of Comparison Statistics","volume":"17","author":"L Wan","year":"2010","journal-title":"Journal of Computational Biology"},{"key":"ref22","article-title":"Statistically-Consistent k-Mer Methods for Phylogenetic Tree Reconstruction","author":"ES Allman","year":"2015","journal-title":"Statistically-Consistent k-Mer Methods for Phylogenetic Tree Reconstruction"},{"issue":"7","key":"ref23","doi-asserted-by":"crossref","first-page":"993","DOI":"10.1093\/bioinformatics\/btv395","article-title":"Inference of Markovian Properties of Molecular Sequences from NGS Data and Applications to Comparative Genomics","volume":"32","author":"J Ren","year":"2016","journal-title":"Bioinformatics"},{"issue":"2","key":"ref24","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1089\/cmb.2012.0228","article-title":"Alignment-Free Sequence Comparison Based on Next-Generation Sequencing Reads","volume":"20","author":"K Song","year":"2013","journal-title":"Journal of Computational Biology"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"730","DOI":"10.1186\/1471-2164-13-730","article-title":"Comparison of Metagenomic Samples Using Sequence Signatures","volume":"13","author":"B Jiang","year":"2012","journal-title":"BMC Genomics"},{"issue":"1","key":"ref26","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.jalgor.2003.12.001","article-title":"An improved data stream summary: the count-min sketch and its applications","volume":"55","author":"G Cormode","year":"2004","journal-title":"Journal of Algorithms"},{"issue":"7","key":"ref27","doi-asserted-by":"crossref","first-page":"e101271","DOI":"10.1371\/journal.pone.0101271","article-title":"These Are Not the K-Mers You Are Looking For: Efficient Online K-Mer Counting Using a Probabilistic Data Structure","volume":"9","author":"Q Zhang","year":"2014","journal-title":"PLoS ONE"},{"key":"ref28","article-title":"The Khmer Software Package: Enabling Efficient Nucleotide Sequence Analysis","author":"MR Crusoe","year":"2015","journal-title":"F1000Research"},{"issue":"40","key":"ref29","doi-asserted-by":"crossref","first-page":"17077","DOI":"10.1073\/pnas.0909377106","article-title":"Whole-genome phylogeny of mammals: evolutionary information in genic and nongenic regions","volume":"106","author":"GE Sims","year":"2009","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"3","key":"ref30","doi-asserted-by":"crossref","first-page":"1171","DOI":"10.1214\/009053607000000677","article-title":"Kernel Methods in Machine Learning","volume":"36","author":"T Hofmann","year":"2008","journal-title":"The Annals of Statistics"},{"key":"ref31","unstructured":"Guennebaud G, Jacob B, others. Eigen V3; 2010."},{"issue":"1","key":"ref32","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1186\/2047-217X-3-8","article-title":"The 3,000 Rice Genomes Project: New Opportunities and Challenges for Future Rice Research","volume":"3","author":"JY Li","year":"2014","journal-title":"GigaScience"},{"issue":"1","key":"ref33","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1186\/2047-217X-3-7","article-title":"The 3,000 Rice Genomes Project","volume":"3","year":"2014","journal-title":"GigaScience"},{"issue":"9","key":"ref34","doi-asserted-by":"crossref","first-page":"2353","DOI":"10.1105\/tpc.15.00492","article-title":"Whole-Genome Resequencing Reveals Extensive Natural Variation in the Model Green Alga Chlamydomonas Reinhardtii","volume":"27","author":"JM Flowers","year":"2015","journal-title":"The Plant Cell"},{"issue":"8","key":"ref35","doi-asserted-by":"crossref","first-page":"E911","DOI":"10.1073\/pnas.1414592112","article-title":"Structure, Variation, and Assembly of the Root-Associated Microbiomes of Rice","volume":"112","author":"J Edwards","year":"2015","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"ref36","article-title":"A Reference-Free Algorithm for Computational Normalization of Shotgun Sequencing Data","author":"CT Brown","year":"2012"},{"issue":"24","key":"ref37","doi-asserted-by":"crossref","first-page":"3326","DOI":"10.1093\/bioinformatics\/bts606","article-title":"A High-Performance Computing Toolset for Relatedness and Principal Component Analysis of SNP Data","volume":"28","author":"X Zheng","year":"2012","journal-title":"Bioinformatics"},{"issue":"10","key":"ref38","doi-asserted-by":"crossref","first-page":"e1000686","DOI":"10.1371\/journal.pgen.1000686","article-title":"A Genealogical Interpretation of Principal Components Analysis","volume":"5","author":"G McVean","year":"2009","journal-title":"PLOS Genet"},{"key":"ref39","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1186\/1471-2105-12-333","article-title":"Efficient Counting of k-Mers in DNA Sequences Using a Bloom Filter","volume":"12","author":"P Melsted","year":"2011","journal-title":"BMC bioinformatics"},{"issue":"5","key":"ref40","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","article-title":"Term-Weighting Approaches in Automatic Text Retrieval","volume":"24","author":"G Salton","year":"1988","journal-title":"Information Processing & Management"},{"key":"ref41","doi-asserted-by":"crossref","unstructured":"Chen S, Goodman J. An Empirical Study of Smoothing Techniques for Language Modeling. In: Proceedings of the 34th Annual Meeting of the ACL; 1996. p. 310\u2013318.","DOI":"10.3115\/981863.981904"},{"key":"ref42","first-page":"1435","article-title":"Fast String Kernels Using Inexact Matching for Protein Sequences","volume":"5","author":"C Leslie","year":"2004","journal-title":"J Mach Learn Res"},{"issue":"4","key":"ref43","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1093\/bioinformatics\/btg431","article-title":"Mismatch String Kernels for Discriminative Protein Classification","volume":"20","author":"CS Leslie","year":"2004","journal-title":"Bioinformatics (Oxford, England)"},{"key":"ref44","doi-asserted-by":"crossref","unstructured":"Leslie C, Eskin E, Noble WS. The Spectrum Kernel: A String Kernel for SVM Protein Classification. Pacific Symposium on Biocomputing Pacific Symposium on Biocomputing. 2002; p. 564\u2013575.","DOI":"10.1142\/9789812799623_0053"},{"key":"ref45","doi-asserted-by":"crossref","unstructured":"Gog S, Beller T, Moffat A, Petri M. From Theory to Practice: Plug and Play with Succinct Data Structures. In: Gudmundsson J, Katajainen J, editors. Experimental Algorithms: 13th International Symposium, SEA 2014, Copenhagen, Denmark, June 29\u2014July 1, 2014. Proceedings. Cham: Springer International Publishing; 2014. p. 326\u2013337.","DOI":"10.1007\/978-3-319-07959-2_28"},{"issue":"3","key":"ref46","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1038\/nbt.3442","article-title":"Fast Search of Thousands of Short-Read Sequencing Experiments","volume":"34","author":"B Solomon","year":"2016","journal-title":"Nature Biotechnology"},{"issue":"10","key":"ref47","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1186\/gb-2011-12-10-232","article-title":"Genome-Wide Association Studies in Plants: The Missing Heritability Is in the Field","volume":"12","author":"B Brachi","year":"2011","journal-title":"Genome biology"},{"key":"ref48","first-page":"n\/a","article-title":"When More Is Better: How Data Sharing Would Accelerate Genomic Selection of Crop Plants","author":"JE Spindel","year":"2016","journal-title":"New Phytologist"},{"issue":"19","key":"ref49","doi-asserted-by":"crossref","first-page":"2520","DOI":"10.1093\/bioinformatics\/bts480","article-title":"Snakemake\u2014a Scalable Bioinformatics Workflow Engine","volume":"28","author":"J K\u00f6ster","year":"2012","journal-title":"Bioinformatics"},{"issue":"3","key":"ref50","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/MCSE.2007.53","article-title":"IPython: A System for Interactive Scientific Computing","volume":"9","author":"F Perez","year":"2007","journal-title":"Computing in Science & Engineering"},{"key":"ref51","doi-asserted-by":"crossref","unstructured":"Kluyver T, Ragan-Kelley B, P\u00e9rez F, Granger B, Bussonnier M, Frederic J, et al. Jupyter Notebooks\u2014a Publishing Format for Reproducible Computational Workflows. In: Positioning and Power in Academic Publishing: Players, Agents and Agendas: Proceedings of the 20th International Conference on Electronic Publishing. IOS Press; 2016. p. 87.","DOI":"10.3233\/978-1-61499-649-1-87"},{"issue":"10","key":"ref52","doi-asserted-by":"crossref","first-page":"1680","DOI":"10.1093\/bioinformatics\/btu861","article-title":"Scrm: Efficiently Simulating Long Sequences Using the Approximated Coalescent with Recombination","volume":"31","author":"PR Staab","year":"2015","journal-title":"Bioinformatics"},{"issue":"Suppl 3","key":"ref53","doi-asserted-by":"crossref","first-page":"iii31","DOI":"10.1093\/bioinformatics\/bti1200","article-title":"DNA Assembly with Gaps (Dawg): Simulating Sequence Evolution","volume":"21","author":"RA Cartwright","year":"2005","journal-title":"Bioinformatics"},{"key":"ref54","unstructured":"Holtgrewe M. Mason\u2014A Read Simulator for Second Generation Sequencing Data. Technical Report FU Berlin. 2010;."},{"key":"ref55","unstructured":"Jones E, Oliphant T, Peterson P. SciPy: Open Source Scientific Tools for Python; 2001\u2013."},{"key":"ref56","unstructured":"Murray K. SRApy: Pythonic Tools for Accessing the Short Read Archive. Zenodo. 2016;"},{"key":"ref57","unstructured":"Joshi NA, Fass JN. Sickle: A Sliding-Window, Adaptive, Quality-Based Trimming Tool for FastQ Files; 2011."},{"key":"ref58","article-title":"Springer Series in Statistics","author":"T Hastie","year":"2009"},{"key":"ref59","article-title":"R: A Language and Environment for Statistical Computing","year":"2016"},{"key":"ref60","unstructured":"Li H. Seqtk\u2014Toolkit for Processing Sequences in FASTA\/Q Formats; 2008. <ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/lh3\/seqtk\" xlink:type=\"simple\">https:\/\/github.com\/lh3\/seqtk<\/ext-link>."}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1005727","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2017,9,15]],"date-time":"2017-09-15T00:00:00Z","timestamp":1505433600000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pcbi.1005727","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T11:48:47Z","timestamp":1750852127000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1005727"}},"subtitle":[],"editor":[{"given":"Andreas","family":"Prlic","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2017,9,5]]},"references-count":60,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2017,9,5]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1005727","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/075481","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,9,5]]}}}